Instructions to use Ba2han/experimental_auto with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ba2han/experimental_auto with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Ba2han/experimental_auto", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ba2han/experimental_auto", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Ba2han/experimental_auto", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ba2han/experimental_auto with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ba2han/experimental_auto"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/experimental_auto",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ba2han/experimental_auto

SGLang

How to use Ba2han/experimental_auto with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Ba2han/experimental_auto" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/experimental_auto",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Ba2han/experimental_auto" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/experimental_auto",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use Ba2han/experimental_auto with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ba2han/experimental_auto to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ba2han/experimental_auto to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ba2han/experimental_auto to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ba2han/experimental_auto",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ba2han/experimental_auto with Docker Model Runner:
```
docker model run hf.co/Ba2han/experimental_auto
```

Ba2han commited on 13 days ago

Commit

10dc0a5

verified ·

1 Parent(s): e3b6b8c

Training in progress, step 50, checkpoint

Browse files

Files changed (4) hide show

last-checkpoint/model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/trainer_state.json +158 -158
last-checkpoint/training_args.bin +1 -1

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61b4ce55f856a67bfdbd003ebe9b33428ea067be73223fd9c3bf1c9940e96dfe
 size 1008303016

 version https://git-lfs.github.com/spec/v1
+oid sha256:df7f3da2bd850f33f7298372ff869be8f81c2b3405227fe6c9bd7c6f2f71a131
 size 1008303016

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82d52d99bf15dccd952a3b4f736ae5075d180cf8f005d3c384238593828d1df
 size 1086712487

 version https://git-lfs.github.com/spec/v1
+oid sha256:dc159d75d63a73fbd137e19fda0856ce4e3720ab62cac1e9b38b17fedbdf4bf8
 size 1086712487

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2140468227424749,
   "eval_steps": 50,
   "global_step": 50,
   "is_hyper_param_search": false,
@@ -10,368 +10,368 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.004280936454849498,
-      "grad_norm": 2.3125,
       "learning_rate": 0.0,
-      "loss": 10.99751091003418,
       "step": 1
     },
     {
-      "epoch": 0.008561872909698997,
-      "grad_norm": 2.21875,
       "learning_rate": 0.0125,
-      "loss": 10.999887466430664,
       "step": 2
     },
     {
-      "epoch": 0.012842809364548496,
-      "grad_norm": 1.875,
       "learning_rate": 0.025,
-      "loss": 10.661027908325195,
       "step": 3
     },
     {
-      "epoch": 0.017123745819397993,
-      "grad_norm": 1.453125,
       "learning_rate": 0.02499842659592344,
-      "loss": 10.258359909057617,
       "step": 4
     },
     {
-      "epoch": 0.02140468227424749,
-      "grad_norm": 1.6484375,
       "learning_rate": 0.024993706779789817,
-      "loss": 10.03167724609375,
       "step": 5
     },
     {
-      "epoch": 0.02568561872909699,
-      "grad_norm": 2.65625,
       "learning_rate": 0.0249858417397876,
-      "loss": 10.06635856628418,
       "step": 6
     },
     {
-      "epoch": 0.02996655518394649,
-      "grad_norm": 1.3515625,
       "learning_rate": 0.024974833455898557,
-      "loss": 9.684752464294434,
       "step": 7
     },
     {
-      "epoch": 0.034247491638795986,
-      "grad_norm": 3.03125,
       "learning_rate": 0.024960684699399282,
-      "loss": 9.619985580444336,
       "step": 8
     },
     {
-      "epoch": 0.038528428093645484,
-      "grad_norm": 1.2109375,
       "learning_rate": 0.024943399032163558,
-      "loss": 9.322598457336426,
       "step": 9
     },
     {
-      "epoch": 0.04280936454849498,
-      "grad_norm": 1.203125,
       "learning_rate": 0.024922980805765677,
-      "loss": 9.167491912841797,
       "step": 10
     },
     {
-      "epoch": 0.04709030100334448,
-      "grad_norm": 1.1171875,
       "learning_rate": 0.024899435160384942,
-      "loss": 8.97598934173584,
       "step": 11
     },
     {
-      "epoch": 0.05137123745819398,
-      "grad_norm": 1.09375,
       "learning_rate": 0.02487276802351166,
-      "loss": 8.841875076293945,
       "step": 12
     },
     {
-      "epoch": 0.05565217391304348,
-      "grad_norm": 0.8125,
       "learning_rate": 0.02484298610845493,
-      "loss": 8.693690299987793,
       "step": 13
     },
     {
-      "epoch": 0.05993311036789298,
-      "grad_norm": 0.80859375,
       "learning_rate": 0.024810096912652603,
-      "loss": 8.540060997009277,
       "step": 14
     },
     {
-      "epoch": 0.06421404682274247,
-      "grad_norm": 0.62109375,
       "learning_rate": 0.024774108715783835,
-      "loss": 8.427875518798828,
       "step": 15
     },
     {
-      "epoch": 0.06849498327759197,
-      "grad_norm": 0.703125,
       "learning_rate": 0.02473503057768474,
-      "loss": 8.279977798461914,
       "step": 16
     },
     {
-      "epoch": 0.07277591973244148,
-      "grad_norm": 0.6640625,
       "learning_rate": 0.02469287233606759,
-      "loss": 8.238062858581543,
       "step": 17
     },
     {
-      "epoch": 0.07705685618729097,
-      "grad_norm": 0.60546875,
       "learning_rate": 0.024647644604044273,
-      "loss": 8.140103340148926,
       "step": 18
     },
     {
-      "epoch": 0.08133779264214047,
-      "grad_norm": 0.6171875,
       "learning_rate": 0.024599358767454456,
-      "loss": 8.044753074645996,
       "step": 19
     },
     {
-      "epoch": 0.08561872909698996,
-      "grad_norm": 0.515625,
       "learning_rate": 0.024548026981999278,
-      "loss": 7.991354465484619,
       "step": 20
     },
     {
-      "epoch": 0.08989966555183947,
-      "grad_norm": 0.57421875,
       "learning_rate": 0.02449366217018122,
-      "loss": 7.921579837799072,
       "step": 21
     },
     {
-      "epoch": 0.09418060200668896,
-      "grad_norm": 0.65234375,
       "learning_rate": 0.024436278018050924,
-      "loss": 7.871639728546143,
       "step": 22
     },
     {
-      "epoch": 0.09846153846153846,
-      "grad_norm": 0.50390625,
       "learning_rate": 0.02437588897176182,
-      "loss": 7.7901129722595215,
       "step": 23
     },
     {
-      "epoch": 0.10274247491638797,
-      "grad_norm": 0.458984375,
       "learning_rate": 0.024312510233933354,
-      "loss": 7.722414016723633,
       "step": 24
     },
     {
-      "epoch": 0.10702341137123746,
-      "grad_norm": 0.671875,
       "learning_rate": 0.024246157759823857,
-      "loss": 7.714761257171631,
       "step": 25
     },
     {
-      "epoch": 0.11130434782608696,
-      "grad_norm": 0.73828125,
       "learning_rate": 0.024176848253313836,
-      "loss": 7.689679145812988,
       "step": 26
     },
     {
-      "epoch": 0.11558528428093645,
-      "grad_norm": 0.466796875,
       "learning_rate": 0.02410459916270091,
-      "loss": 7.656161308288574,
       "step": 27
     },
     {
-      "epoch": 0.11986622073578596,
       "grad_norm": 0.373046875,
       "learning_rate": 0.02402942867630727,
-      "loss": 7.593247890472412,
       "step": 28
     },
     {
-      "epoch": 0.12414715719063545,
-      "grad_norm": 0.365234375,
       "learning_rate": 0.02395135571790087,
-      "loss": 7.558600902557373,
       "step": 29
     },
     {
-      "epoch": 0.12842809364548494,
-      "grad_norm": 0.392578125,
       "learning_rate": 0.02387039994193148,
-      "loss": 7.517961502075195,
       "step": 30
     },
     {
-      "epoch": 0.13270903010033444,
-      "grad_norm": 0.48828125,
       "learning_rate": 0.023786581728582768,
-      "loss": 7.4646525382995605,
       "step": 31
     },
     {
-      "epoch": 0.13698996655518395,
-      "grad_norm": 0.41015625,
       "learning_rate": 0.023699922178641697,
-      "loss": 7.4094624519348145,
       "step": 32
     },
     {
-      "epoch": 0.14127090301003345,
-      "grad_norm": 0.376953125,
       "learning_rate": 0.023610443108186545,
-      "loss": 7.402709484100342,
       "step": 33
     },
     {
-      "epoch": 0.14555183946488295,
-      "grad_norm": 0.361328125,
       "learning_rate": 0.023518167043094777,
-      "loss": 7.354226112365723,
       "step": 34
     },
     {
-      "epoch": 0.14983277591973243,
-      "grad_norm": 0.38671875,
       "learning_rate": 0.023423117213372313,
-      "loss": 7.302793502807617,
       "step": 35
     },
     {
-      "epoch": 0.15411371237458193,
-      "grad_norm": 0.484375,
       "learning_rate": 0.023325317547305487,
-      "loss": 7.298144817352295,
       "step": 36
     },
     {
-      "epoch": 0.15839464882943144,
-      "grad_norm": 0.56640625,
       "learning_rate": 0.023224792665437213,
-      "loss": 7.267189979553223,
       "step": 37
     },
     {
-      "epoch": 0.16267558528428094,
-      "grad_norm": 0.4140625,
       "learning_rate": 0.023121567874368934,
-      "loss": 7.22215461730957,
       "step": 38
     },
     {
-      "epoch": 0.16695652173913045,
-      "grad_norm": 0.47265625,
       "learning_rate": 0.023015669160389766,
-      "loss": 7.1571245193481445,
       "step": 39
     },
     {
-      "epoch": 0.17123745819397992,
-      "grad_norm": 0.466796875,
       "learning_rate": 0.02290712318293464,
-      "loss": 7.14966344833374,
       "step": 40
     },
     {
-      "epoch": 0.17551839464882943,
-      "grad_norm": 0.486328125,
       "learning_rate": 0.02279595726787291,
-      "loss": 7.105873107910156,
       "step": 41
     },
     {
-      "epoch": 0.17979933110367893,
-      "grad_norm": 0.46875,
       "learning_rate": 0.022682199400629197,
-      "loss": 7.067068099975586,
       "step": 42
     },
     {
-      "epoch": 0.18408026755852844,
-      "grad_norm": 0.49609375,
       "learning_rate": 0.022565878219138233,
-      "loss": 7.027277946472168,
       "step": 43
     },
     {
-      "epoch": 0.18836120401337791,
-      "grad_norm": 0.390625,
       "learning_rate": 0.022447023006635404,
-      "loss": 6.947190761566162,
       "step": 44
     },
     {
-      "epoch": 0.19264214046822742,
-      "grad_norm": 0.40234375,
       "learning_rate": 0.022325663684284847,
-      "loss": 6.984321594238281,
       "step": 45
     },
     {
-      "epoch": 0.19692307692307692,
-      "grad_norm": 0.40234375,
       "learning_rate": 0.02220183080364696,
-      "loss": 6.949177265167236,
       "step": 46
     },
     {
-      "epoch": 0.20120401337792643,
-      "grad_norm": 0.353515625,
       "learning_rate": 0.022075555538987227,
-      "loss": 6.896018028259277,
       "step": 47
     },
     {
-      "epoch": 0.20548494983277593,
-      "grad_norm": 0.41015625,
       "learning_rate": 0.02194686967942823,
-      "loss": 6.808597564697266,
       "step": 48
     },
     {
-      "epoch": 0.2097658862876254,
-      "grad_norm": 0.408203125,
       "learning_rate": 0.021815805620946937,
-      "loss": 6.824460983276367,
       "step": 49
     },
     {
-      "epoch": 0.2140468227424749,
-      "grad_norm": 0.4453125,
       "learning_rate": 0.021682396358219166,
-      "loss": 6.777248382568359,
       "step": 50
     },
     {
-      "epoch": 0.2140468227424749,
-      "eval_loss": 6.7472333908081055,
-      "eval_runtime": 51.7313,
-      "eval_samples_per_second": 11.811,
-      "eval_steps_per_second": 2.958,
       "step": 50
     }
   ],
   "logging_steps": 1,
   "max_steps": 200,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -385,8 +385,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.645919305579571e+16,
-  "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null
 }

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 0.4280936454849498,
   "eval_steps": 50,
   "global_step": 50,
   "is_hyper_param_search": false,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "epoch": 0.008561872909698997,
+      "grad_norm": 2.1875,
       "learning_rate": 0.0,
+      "loss": 11.000052452087402,
       "step": 1
     },
     {
+      "epoch": 0.017123745819397993,
+      "grad_norm": 2.15625,
       "learning_rate": 0.0125,
+      "loss": 11.001190185546875,
       "step": 2
     },
     {
+      "epoch": 0.02568561872909699,
+      "grad_norm": 1.7890625,
       "learning_rate": 0.025,
+      "loss": 10.639176368713379,
       "step": 3
     },
     {
+      "epoch": 0.034247491638795986,
+      "grad_norm": 1.484375,
       "learning_rate": 0.02499842659592344,
+      "loss": 10.244665145874023,
       "step": 4
     },
     {
+      "epoch": 0.04280936454849498,
+      "grad_norm": 1.6796875,
       "learning_rate": 0.024993706779789817,
+      "loss": 10.011271476745605,
       "step": 5
     },
     {
+      "epoch": 0.05137123745819398,
+      "grad_norm": 2.671875,
       "learning_rate": 0.0249858417397876,
+      "loss": 9.91366958618164,
       "step": 6
     },
     {
+      "epoch": 0.05993311036789298,
+      "grad_norm": 2.0,
       "learning_rate": 0.024974833455898557,
+      "loss": 9.735193252563477,
       "step": 7
     },
     {
+      "epoch": 0.06849498327759197,
+      "grad_norm": 1.2890625,
       "learning_rate": 0.024960684699399282,
+      "loss": 9.460551261901855,
       "step": 8
     },
     {
+      "epoch": 0.07705685618729097,
+      "grad_norm": 1.0546875,
       "learning_rate": 0.024943399032163558,
+      "loss": 9.263848304748535,
       "step": 9
     },
     {
+      "epoch": 0.08561872909698996,
+      "grad_norm": 1.1796875,
       "learning_rate": 0.024922980805765677,
+      "loss": 9.114842414855957,
       "step": 10
     },
     {
+      "epoch": 0.09418060200668896,
+      "grad_norm": 0.8984375,
       "learning_rate": 0.024899435160384942,
+      "loss": 8.910664558410645,
       "step": 11
     },
     {
+      "epoch": 0.10274247491638797,
+      "grad_norm": 0.90234375,
       "learning_rate": 0.02487276802351166,
+      "loss": 8.746124267578125,
       "step": 12
     },
     {
+      "epoch": 0.11130434782608696,
+      "grad_norm": 0.921875,
       "learning_rate": 0.02484298610845493,
+      "loss": 8.617627143859863,
       "step": 13
     },
     {
+      "epoch": 0.11986622073578596,
+      "grad_norm": 0.6875,
       "learning_rate": 0.024810096912652603,
+      "loss": 8.474465370178223,
       "step": 14
     },
     {
+      "epoch": 0.12842809364548494,
+      "grad_norm": 0.69921875,
       "learning_rate": 0.024774108715783835,
+      "loss": 8.355995178222656,
       "step": 15
     },
     {
+      "epoch": 0.13698996655518395,
+      "grad_norm": 0.6328125,
       "learning_rate": 0.02473503057768474,
+      "loss": 8.227234840393066,
       "step": 16
     },
     {
+      "epoch": 0.14555183946488295,
+      "grad_norm": 0.69921875,
       "learning_rate": 0.02469287233606759,
+      "loss": 8.151434898376465,
       "step": 17
     },
     {
+      "epoch": 0.15411371237458193,
+      "grad_norm": 0.58203125,
       "learning_rate": 0.024647644604044273,
+      "loss": 8.038224220275879,
       "step": 18
     },
     {
+      "epoch": 0.16267558528428094,
+      "grad_norm": 0.56640625,
       "learning_rate": 0.024599358767454456,
+      "loss": 7.988001346588135,
       "step": 19
     },
     {
+      "epoch": 0.17123745819397992,
+      "grad_norm": 0.76953125,
       "learning_rate": 0.024548026981999278,
+      "loss": 7.911329746246338,
       "step": 20
     },
     {
+      "epoch": 0.17979933110367893,
+      "grad_norm": 0.50390625,
       "learning_rate": 0.02449366217018122,
+      "loss": 7.835102558135986,
       "step": 21
     },
     {
+      "epoch": 0.18836120401337791,
+      "grad_norm": 0.447265625,
       "learning_rate": 0.024436278018050924,
+      "loss": 7.749161720275879,
       "step": 22
     },
     {
+      "epoch": 0.19692307692307692,
+      "grad_norm": 0.470703125,
       "learning_rate": 0.02437588897176182,
+      "loss": 7.731137752532959,
       "step": 23
     },
     {
+      "epoch": 0.20548494983277593,
+      "grad_norm": 0.54296875,
       "learning_rate": 0.024312510233933354,
+      "loss": 7.658270835876465,
       "step": 24
     },
     {
+      "epoch": 0.2140468227424749,
+      "grad_norm": 0.515625,
       "learning_rate": 0.024246157759823857,
+      "loss": 7.607485771179199,
       "step": 25
     },
     {
+      "epoch": 0.22260869565217392,
+      "grad_norm": 0.40625,
       "learning_rate": 0.024176848253313836,
+      "loss": 7.570281028747559,
       "step": 26
     },
     {
+      "epoch": 0.2311705685618729,
+      "grad_norm": 0.55078125,
       "learning_rate": 0.02410459916270091,
+      "loss": 7.528012275695801,
       "step": 27
     },
     {
+      "epoch": 0.2397324414715719,
       "grad_norm": 0.373046875,
       "learning_rate": 0.02402942867630727,
+      "loss": 7.462031364440918,
       "step": 28
     },
     {
+      "epoch": 0.2482943143812709,
+      "grad_norm": 0.3671875,
       "learning_rate": 0.02395135571790087,
+      "loss": 7.411103248596191,
       "step": 29
     },
     {
+      "epoch": 0.2568561872909699,
+      "grad_norm": 0.4453125,
       "learning_rate": 0.02387039994193148,
+      "loss": 7.400269031524658,
       "step": 30
     },
     {
+      "epoch": 0.2654180602006689,
+      "grad_norm": 0.427734375,
       "learning_rate": 0.023786581728582768,
+      "loss": 7.331328392028809,
       "step": 31
     },
     {
+      "epoch": 0.2739799331103679,
+      "grad_norm": 0.58203125,
       "learning_rate": 0.023699922178641697,
+      "loss": 7.33138370513916,
       "step": 32
     },
     {
+      "epoch": 0.2825418060200669,
+      "grad_norm": 0.484375,
       "learning_rate": 0.023610443108186545,
+      "loss": 7.266662120819092,
       "step": 33
     },
     {
+      "epoch": 0.2911036789297659,
+      "grad_norm": 0.5,
       "learning_rate": 0.023518167043094777,
+      "loss": 7.242274284362793,
       "step": 34
     },
     {
+      "epoch": 0.29966555183946486,
+      "grad_norm": 0.431640625,
       "learning_rate": 0.023423117213372313,
+      "loss": 7.186635494232178,
       "step": 35
     },
     {
+      "epoch": 0.30822742474916387,
+      "grad_norm": 0.458984375,
       "learning_rate": 0.023325317547305487,
+      "loss": 7.136233806610107,
       "step": 36
     },
     {
+      "epoch": 0.3167892976588629,
+      "grad_norm": 0.396484375,
       "learning_rate": 0.023224792665437213,
+      "loss": 7.15239143371582,
       "step": 37
     },
     {
+      "epoch": 0.3253511705685619,
+      "grad_norm": 0.390625,
       "learning_rate": 0.023121567874368934,
+      "loss": 7.045711040496826,
       "step": 38
     },
     {
+      "epoch": 0.3339130434782609,
+      "grad_norm": 0.3359375,
       "learning_rate": 0.023015669160389766,
+      "loss": 7.051828384399414,
       "step": 39
     },
     {
+      "epoch": 0.34247491638795985,
+      "grad_norm": 0.35546875,
       "learning_rate": 0.02290712318293464,
+      "loss": 6.995121479034424,
       "step": 40
     },
     {
+      "epoch": 0.35103678929765886,
+      "grad_norm": 0.34375,
       "learning_rate": 0.02279595726787291,
+      "loss": 6.917529106140137,
       "step": 41
     },
     {
+      "epoch": 0.35959866220735787,
+      "grad_norm": 0.408203125,
       "learning_rate": 0.022682199400629197,
+      "loss": 6.943573474884033,
       "step": 42
     },
     {
+      "epoch": 0.3681605351170569,
+      "grad_norm": 0.486328125,
       "learning_rate": 0.022565878219138233,
+      "loss": 6.849137306213379,
       "step": 43
     },
     {
+      "epoch": 0.37672240802675583,
+      "grad_norm": 0.431640625,
       "learning_rate": 0.022447023006635404,
+      "loss": 6.817243576049805,
       "step": 44
     },
     {
+      "epoch": 0.38528428093645484,
+      "grad_norm": 0.466796875,
       "learning_rate": 0.022325663684284847,
+      "loss": 6.751210689544678,
       "step": 45
     },
     {
+      "epoch": 0.39384615384615385,
+      "grad_norm": 0.44140625,
       "learning_rate": 0.02220183080364696,
+      "loss": 6.731540679931641,
       "step": 46
     },
     {
+      "epoch": 0.40240802675585285,
+      "grad_norm": 0.4140625,
       "learning_rate": 0.022075555538987227,
+      "loss": 6.705706596374512,
       "step": 47
     },
     {
+      "epoch": 0.41096989966555186,
+      "grad_norm": 0.345703125,
       "learning_rate": 0.02194686967942823,
+      "loss": 6.678059101104736,
       "step": 48
     },
     {
+      "epoch": 0.4195317725752508,
+      "grad_norm": 0.4140625,
       "learning_rate": 0.021815805620946937,
+      "loss": 6.6417555809021,
       "step": 49
     },
     {
+      "epoch": 0.4280936454849498,
+      "grad_norm": 0.462890625,
       "learning_rate": 0.021682396358219166,
+      "loss": 6.592331886291504,
       "step": 50
     },
     {
+      "epoch": 0.4280936454849498,
+      "eval_loss": 6.548539638519287,
+      "eval_runtime": 51.5345,
+      "eval_samples_per_second": 11.856,
+      "eval_steps_per_second": 2.969,
       "step": 50
     }
   ],
   "logging_steps": 1,
   "max_steps": 200,
   "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
     "TrainerControl": {
       "attributes": {}
     }
   },
+  "total_flos": 7.292068282073088e+16,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25d686833094b637e69f7be1bd7dd0c173bb768a2a8b1916830852d7703b16ed
 size 5713

 version https://git-lfs.github.com/spec/v1
+oid sha256:9224b9e115d57261205215ceae02ffa4a6e8577fbe762a2cbd2cd5c8a9f1ea82
 size 5713